Buckets:
7.38 GB
7 files
Updated 4 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.84 kB xet | 7e0ddc1c | |
| Confucius4-R2T2-Q4_K_M.gguf | 1.11 GB xet | e567f04c | |
| Confucius4-R2T2-Q8_0.gguf | 1.83 GB xet | c2d56300 | |
| Confucius4-R2T2-f16.gguf | 3.45 GB xet | 86b512b8 | |
| README.md | 3.8 kB xet | 74dd565b | |
| mmproj-Confucius4-R2T2-Q8_0.gguf | 348 MB xet | 20b42ffc | |
| mmproj-Confucius4-R2T2-f16.gguf | 642 MB xet | 42052b6b |
Confucius4-R2T2: A Low Latency and High Accuracy Real-Time Speech Recognition Model
Real Real-Time Transcription
Confucius4-R2T2-GGUF
Official GGUF release from NetEase Youdao for netease-youdao/Confucius4-R2T2, a low-latency and high-accuracy true streaming Automatic Speech Recognition (ASR) model that features fine-grained and configurable decoding chunks from 80 ms to 2 s.
Files
| Filename | Quantization | Size | Notes |
|---|---|---|---|
| Confucius4-R2T2-f16.gguf | f16 | 3.2GiB | best quality |
| Confucius4-R2T2-Q8_0.gguf | Q8_0 | 1.7GiB | very good quality |
| Confucius4-R2T2-Q4_K_M.gguf | Q4_K_M | 1.0GiB | fast, lower quality |
| mmproj-Confucius4-R2T2-f16.gguf | mmproj-f16 | 0.6GiB | multi-modal supplement |
| mmproj-Confucius4-R2T2-Q8_0.gguf | mmproj-Q8_0 | 0.3GiB | multi-modal supplement |
The low-bit variants are quantized from the f16 GGUF.
- Total size
- 7.38 GB
- Files
- 7
- Last updated
- Oct 7
- Pre-warmed CDN
- US EU US EU